High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

RA-MVS		99.64 1	99.81 1	99.43 2	99.76 2	99.83 3	99.49 25	98.35 4	99.82 1	99.73 1	99.74 3	99.99 1	99.49 19	99.71 2	99.70 1	99.79 33	99.89 13

DELS-MVS		98.19 57	98.77 63	97.52 56	98.29 66	99.71 17	99.12 45	94.58 67	98.80 126	95.38 57	96.24 141	98.24 79	97.92 134	99.06 44	99.52 2	99.82 17	99.79 47
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DeepC-MVS	97.63 4	98.33 52	98.57 66	98.04 44	98.62 61	99.65 25	99.45 30	98.15 27	99.51 19	92.80 123	95.74 156	96.44 97	99.46 25	99.37 22	99.50 3	99.78 37	99.81 37
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	96.92 7	98.67 41	99.05 49	98.23 40	99.57 30	99.45 76	99.11 46	94.66 62	99.69 6	96.80 36	96.55 132	99.61 57	99.40 29	98.87 62	99.49 4	99.85 10	99.66 136

MSLP-MVS++		99.15 21	99.24 39	99.04 18	99.52 36	99.49 67	99.09 48	98.07 33	99.37 35	98.47 12	97.79 88	99.89 39	99.50 16	98.93 54	99.45 5	99.61 153	99.76 69

IS_MVSNet		97.86 63	98.86 59	96.68 83	96.02 109	99.72 14	98.35 86	93.37 96	98.75 138	94.01 90	96.88 119	98.40 76	98.48 113	99.09 41	99.42 6	99.83 15	99.80 39

MVSMamba_PlusPlus		98.20 56	99.31 34	96.90 78	95.83 119	99.65 25	98.96 57	94.33 73	99.46 23	93.04 116	98.73 58	98.88 69	99.47 23	99.13 40	99.41 7	99.78 37	99.89 13

Vis-MVSNet (Re-imp)		97.40 79	98.89 58	95.66 136	95.99 112	99.62 37	97.82 113	93.22 114	98.82 123	91.40 152	96.94 116	98.56 74	95.70 205	99.14 38	99.41 7	99.79 33	99.75 77

PHI-MVS		99.08 25	99.43 23	98.67 31	99.15 49	99.59 49	99.11 46	97.35 43	99.14 79	97.30 31	99.44 16	99.96 13	99.32 36	98.89 59	99.39 9	99.79 33	99.58 154

APD-MVS		99.25 15	99.38 26	99.09 14	99.69 10	99.58 52	99.56 21	98.32 10	98.85 116	97.87 23	98.91 47	99.92 31	99.30 39	99.45 18	99.38 10	99.79 33	99.58 154
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepPCF-MVS	97.74 3	98.34 51	99.46 16	97.04 69	98.82 56	99.33 118	96.28 186	97.47 42	99.58 11	94.70 75	98.99 40	99.85 44	97.24 157	99.55 11	99.34 11	97.73 244	99.56 161

MGCNet		98.81 36	99.44 20	98.08 42	98.83 55	99.75 10	99.58 20	95.53 50	99.76 2	96.48 42	99.70 5	98.64 71	98.21 121	99.00 50	99.33 12	99.82 17	99.90 7

DeepC-MVS_fast	98.34 1	99.17 20	99.45 17	98.85 27	99.55 33	99.37 105	99.64 10	98.05 35	99.53 16	96.58 38	98.93 45	99.92 31	99.49 19	99.46 17	99.32 13	99.80 32	99.64 143
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		99.38 9	99.60 4	99.12 12	99.76 2	99.62 37	99.39 34	98.23 22	99.52 18	98.03 21	99.45 15	99.98 3	99.64 5	99.58 9	99.30 14	99.68 118	99.76 69
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
3Dnovator+	96.92 7	98.71 40	99.05 49	98.32 36	99.53 34	99.34 113	99.06 50	94.61 63	99.65 8	97.49 28	96.75 120	99.86 42	99.44 27	98.78 68	99.30 14	99.81 25	99.67 132

QAPM		98.62 44	99.04 52	98.13 41	99.57 30	99.48 68	99.17 42	94.78 59	99.57 12	96.16 44	96.73 121	99.80 47	99.33 34	98.79 66	99.29 16	99.75 51	99.64 143

EC-MVSNet		98.22 55	99.44 20	96.79 79	95.62 141	99.56 55	99.01 54	92.22 131	99.17 67	94.51 80	99.41 17	99.62 56	99.49 19	99.16 37	99.26 17	99.91 2	99.94 1

APDe-MVS		99.49 4	99.64 2	99.32 5	99.74 5	99.74 13	99.75 3	98.34 6	99.56 13	98.72 10	99.57 11	99.97 9	99.53 15	99.65 3	99.25 18	99.84 12	99.77 62
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.30 12	99.54 10	99.03 19	99.66 19	99.64 31	99.68 6	98.25 18	99.56 13	97.12 34	99.19 25	99.95 18	99.72 1	99.43 19	99.25 18	99.72 85	99.77 62

HFP-MVS		99.32 11	99.53 12	99.07 16	99.69 10	99.59 49	99.63 14	98.31 11	99.56 13	97.37 30	99.27 23	99.97 9	99.70 3	99.35 25	99.24 20	99.71 96	99.76 69

UA-Net		97.13 94	99.14 43	94.78 145	97.21 84	99.38 99	97.56 135	92.04 134	98.48 153	88.03 170	98.39 73	99.91 35	94.03 236	99.33 27	99.23 21	99.81 25	99.25 193

LS3D		97.79 64	98.25 77	97.26 64	98.40 64	99.63 34	99.53 22	98.63 1	99.25 55	88.13 169	96.93 117	94.14 129	99.19 44	99.14 38	99.23 21	99.69 110	99.42 180

X-MVS		98.93 32	99.37 27	98.42 34	99.67 16	99.62 37	99.60 18	98.15 27	99.08 90	93.81 96	98.46 70	99.95 18	99.59 9	99.49 15	99.21 23	99.68 118	99.75 77

PGM-MVS		98.86 34	99.35 31	98.29 37	99.77 1	99.63 34	99.67 7	95.63 49	98.66 143	95.27 64	99.11 32	99.82 46	99.67 4	99.33 27	99.19 24	99.73 72	99.74 86

SteuartSystems-ACMMP		99.20 18	99.51 14	98.83 29	99.66 19	99.66 24	99.71 5	98.12 31	99.14 79	96.62 37	99.16 27	99.98 3	99.12 53	99.63 4	99.19 24	99.78 37	99.83 31
Skip Steuart: Steuart Systems R&D Blog.
test1111		97.09 96	96.83 159	97.39 58	96.92 92	99.81 4	98.44 78	94.45 69	99.17 67	95.85 48	92.10 207	88.97 187	98.78 87	99.02 47	99.11 26	99.88 4	99.63 147

test2506		97.16 92	96.68 164	97.73 50	96.95 90	99.79 5	98.48 74	94.42 70	99.17 67	97.74 26	99.15 28	80.93 250	98.89 74	99.03 45	99.09 27	99.88 4	99.62 149

ECVR-MVS		97.27 85	97.09 142	97.48 57	96.95 90	99.79 5	98.48 74	94.42 70	99.17 67	96.28 43	93.54 190	89.39 183	98.89 74	99.03 45	99.09 27	99.88 4	99.61 152

CS-MVS		98.56 47	99.32 32	97.68 51	98.28 67	99.89 2	98.71 67	94.53 68	99.41 30	95.43 54	99.05 39	98.66 70	99.19 44	99.21 32	99.07 29	99.93 1	99.94 1

TSAR-MVS + MP.		99.27 13	99.57 7	98.92 25	98.78 58	99.53 59	99.72 4	98.11 32	99.73 4	97.43 29	99.15 28	99.96 13	99.59 9	99.73 1	99.07 29	99.88 4	99.82 32
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
aaEdge-Enhanced		99.51 2	99.57 7	99.44 1	99.71 8	99.65 25	99.83 1	98.29 14	99.50 21	99.61 3	99.69 6	99.94 27	99.50 16	99.50 14	99.06 31	99.71 96	99.64 143

SD-MVS		99.25 15	99.50 15	98.96 23	98.79 57	99.55 57	99.33 37	98.29 14	99.75 3	97.96 22	99.15 28	99.95 18	99.61 6	99.17 35	99.06 31	99.81 25	99.84 27
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
sasdasda		97.31 81	97.81 102	96.72 80	96.20 106	99.45 76	98.21 93	91.60 143	99.22 59	95.39 55	98.48 66	90.95 164	99.16 50	97.66 159	99.05 33	99.76 45	99.90 7

DVP-MVS		99.45 5	99.54 10	99.35 4	99.72 7	99.76 7	99.63 14	98.37 2	99.63 10	99.03 7	98.95 44	99.98 3	99.60 7	99.60 8	99.05 33	99.74 58	99.79 47
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MSP-MVS		99.34 10	99.52 13	99.14 10	99.68 15	99.75 10	99.64 10	98.31 11	99.44 27	98.10 17	99.28 22	99.98 3	99.30 39	99.34 26	99.05 33	99.81 25	99.79 47
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
canonicalmvs		97.31 81	97.81 102	96.72 80	96.20 106	99.45 76	98.21 93	91.60 143	99.22 59	95.39 55	98.48 66	90.95 164	99.16 50	97.66 159	99.05 33	99.76 45	99.90 7

OpenMVS	96.23 11	97.95 62	98.45 71	97.35 59	99.52 36	99.42 93	98.91 59	94.61 63	98.87 113	92.24 141	94.61 179	99.05 68	99.10 55	98.64 80	99.05 33	99.74 58	99.51 172

MGCFI-Net		97.26 87	97.79 105	96.64 87	96.17 108	99.43 88	98.14 100	91.52 148	99.23 56	95.16 67	98.48 66	90.87 166	99.07 58	97.59 165	99.02 38	99.76 45	99.91 6

Vis-MVSNet		96.16 147	98.22 81	93.75 166	95.33 167	99.70 19	97.27 149	90.85 160	98.30 169	85.51 190	95.72 158	96.45 95	93.69 242	98.70 77	99.00 39	99.84 12	99.69 122
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		98.46 48	99.16 42	97.64 53	98.48 63	99.64 31	99.35 36	94.71 61	99.53 16	95.17 66	97.63 95	99.59 58	98.38 118	98.88 61	98.99 40	99.74 58	99.86 23

CDPH-MVS		98.41 49	99.10 45	97.61 54	99.32 46	99.36 107	99.49 25	96.15 48	98.82 123	91.82 148	98.41 71	99.66 55	99.10 55	98.93 54	98.97 41	99.75 51	99.58 154

DPE-MVS		99.39 8	99.55 9	99.20 7	99.63 23	99.71 17	99.66 8	98.33 8	99.29 48	98.40 15	99.64 9	99.98 3	99.31 37	99.56 10	98.96 42	99.85 10	99.70 117
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + ACMM		98.77 37	99.45 17	97.98 46	99.37 41	99.46 72	99.44 32	98.13 30	99.65 8	92.30 137	98.91 47	99.95 18	99.05 59	99.42 20	98.95 43	99.58 172	99.82 32

MED-MVS		99.51 2	99.58 5	99.42 3	99.71 8	99.67 20	99.62 16	98.36 3	99.71 5	99.62 2	99.69 6	99.95 18	99.47 23	99.49 15	98.94 44	99.74 58	99.64 143

EPP-MVSNet		97.75 67	98.71 64	96.63 88	95.68 137	99.56 55	97.51 137	93.10 127	99.22 59	94.99 71	97.18 107	97.30 89	98.65 103	98.83 63	98.93 45	99.84 12	99.92 3

CHOSEN 280x420		97.99 61	99.24 39	96.53 91	98.34 65	99.61 42	98.36 85	89.80 179	99.27 51	95.08 69	99.81 1	98.58 73	98.64 104	99.02 47	98.92 46	98.93 227	99.48 176

CSCG		98.90 33	98.93 57	98.85 27	99.75 4	99.72 14	99.49 25	96.58 46	99.38 33	98.05 20	98.97 42	97.87 82	99.49 19	97.78 150	98.92 46	99.78 37	99.90 7

CHOSEN 1792x2688		96.41 139	96.99 152	95.74 134	98.01 71	99.72 14	97.70 122	90.78 163	99.13 84	90.03 162	87.35 248	95.36 111	98.33 119	98.59 88	98.91 48	99.59 167	99.87 20

MVS_111021_LR		98.67 41	99.41 25	97.81 49	99.37 41	99.53 59	98.51 73	95.52 52	99.27 51	94.85 72	99.56 12	99.69 54	99.04 60	99.36 23	98.88 49	99.60 161	99.58 154

DVP-MVS++		99.41 7	99.64 2	99.14 10	99.69 10	99.75 10	99.64 10	98.33 8	99.67 7	98.10 17	99.66 8	99.99 1	99.33 34	99.62 6	98.86 50	99.74 58	99.90 7

CP-MVS		99.27 13	99.44 20	99.08 15	99.62 25	99.58 52	99.53 22	98.16 25	99.21 62	97.79 24	99.15 28	99.96 13	99.59 9	99.54 12	98.86 50	99.78 37	99.74 86

MAR-MVS		97.71 68	98.04 90	97.32 60	99.35 45	98.91 147	97.65 130	91.68 141	98.00 183	97.01 35	97.72 93	94.83 118	98.85 80	98.44 97	98.86 50	99.41 204	99.52 167
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
SPE-MVS-test		98.58 46	99.42 24	97.60 55	98.52 62	99.91 1	98.60 70	94.60 65	99.37 35	94.62 76	99.40 18	99.16 65	99.39 30	99.36 23	98.85 53	99.90 3	99.92 3

SF-MVS		99.18 19	99.32 32	99.03 19	99.65 21	99.41 96	98.87 60	98.24 21	99.14 79	98.73 9	99.11 32	99.92 31	98.92 68	99.22 31	98.84 54	99.76 45	99.56 161

SED-MVS		99.44 6	99.58 5	99.28 6	99.69 10	99.76 7	99.62 16	98.35 4	99.51 19	99.05 6	99.60 10	99.98 3	99.28 41	99.61 7	98.83 55	99.70 106	99.77 62

MVS_111021_HR		98.59 45	99.36 28	97.68 51	99.42 39	99.61 42	98.14 100	94.81 58	99.31 45	95.00 70	99.51 13	99.79 49	99.00 63	98.94 53	98.83 55	99.69 110	99.57 160

CNLPA		99.03 30	99.05 49	99.01 22	99.27 47	99.22 132	99.03 52	97.98 36	99.34 43	99.00 8	98.25 77	99.71 53	99.31 37	98.80 65	98.82 57	99.48 193	99.17 198

FMVSNet2		96.64 130	97.50 115	95.63 137	93.81 187	97.98 199	98.09 103	90.87 159	98.99 102	93.48 106	93.17 198	95.25 113	97.89 135	98.63 81	98.80 58	99.68 118	99.67 132

MP-MVS		99.07 26	99.36 28	98.74 30	99.63 23	99.57 54	99.66 8	98.25 18	99.00 101	95.62 50	98.97 42	99.94 27	99.54 14	99.51 13	98.79 59	99.71 96	99.73 97
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ETV-MVS		98.05 59	99.25 38	96.65 85	95.61 142	99.61 42	98.26 92	93.52 90	98.90 112	93.74 101	99.32 21	99.20 63	98.90 71	99.21 32	98.72 60	99.87 8	99.79 47

TSAR-MVS + GP.		98.66 43	99.36 28	97.85 48	97.16 86	99.46 72	99.03 52	94.59 66	99.09 87	97.19 33	99.73 4	99.95 18	99.39 30	98.95 52	98.69 61	99.75 51	99.65 139

ACMMP_NAP		99.05 28	99.45 17	98.58 33	99.73 6	99.60 47	99.64 10	98.28 17	99.23 56	94.57 77	99.35 20	99.97 9	99.55 13	99.63 4	98.66 62	99.70 106	99.74 86

OMC-MVS		98.84 35	99.01 54	98.65 32	99.39 40	99.23 131	99.22 39	96.70 45	99.40 31	97.77 25	97.89 87	99.80 47	99.21 42	99.02 47	98.65 63	99.57 176	99.07 205

FMVSNet3		97.02 99	98.12 86	95.73 135	93.59 193	97.98 199	98.34 87	91.32 152	98.80 126	93.92 92	97.21 102	95.94 107	97.63 145	98.61 83	98.62 64	99.61 153	99.65 139

CNVR-MVS		99.23 17	99.28 36	99.17 8	99.65 21	99.34 113	99.46 29	98.21 23	99.28 49	98.47 12	98.89 49	99.94 27	99.50 16	99.42 20	98.61 65	99.73 72	99.52 167

baseline		97.45 77	98.70 65	95.99 129	95.89 114	99.36 107	98.29 88	91.37 151	99.21 62	92.99 118	98.40 72	96.87 94	97.96 133	98.60 86	98.60 66	99.42 203	99.86 23

Casviewmamba		97.31 81	97.93 97	96.58 90	95.74 127	99.47 71	98.19 95	93.31 104	99.17 67	93.45 108	96.43 136	93.34 140	98.98 64	98.82 64	98.55 67	99.82 17	99.75 77

MVS_Test		97.30 84	98.54 67	95.87 131	95.74 127	99.28 123	98.19 95	91.40 150	99.18 66	91.59 150	98.17 79	96.18 102	98.63 105	98.61 83	98.55 67	99.66 132	99.78 55

EPNet		98.05 59	98.86 59	97.10 67	99.02 52	99.43 88	98.47 76	94.73 60	99.05 96	95.62 50	98.93 45	97.62 86	95.48 213	98.59 88	98.55 67	99.29 214	99.84 27
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CVMVSNet		95.33 165	97.09 142	93.27 181	95.23 168	98.39 187	95.49 200	92.58 130	97.71 199	83.00 209	94.44 183	93.28 141	93.92 239	97.79 149	98.54 70	99.41 204	99.45 178

casdiffmvs		96.93 105	97.43 124	96.34 102	95.70 132	99.50 66	97.75 119	93.22 114	98.98 103	92.64 125	94.97 174	91.71 158	98.93 67	98.62 82	98.52 71	99.82 17	99.72 111
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		97.07 97	97.81 102	96.22 109	95.75 126	99.42 93	98.19 95	93.27 109	99.14 79	91.92 146	95.46 165	93.66 134	98.53 111	98.75 72	98.48 72	99.65 137	99.73 97

PVSNet_Blended_VisFu		97.41 78	98.49 70	96.15 118	97.49 76	99.76 7	96.02 191	93.75 86	99.26 53	93.38 109	93.73 188	99.35 61	96.47 179	98.96 51	98.46 73	99.77 43	99.90 7

casdiffmvs_mvg		97.27 85	97.97 95	96.46 96	95.83 119	99.51 65	98.42 79	93.32 101	98.34 167	92.38 135	95.64 159	95.35 112	98.91 69	98.73 75	98.45 74	99.86 9	99.80 39
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DCV-MVSNet		97.56 73	98.36 73	96.62 89	96.44 97	98.36 189	98.37 83	91.73 140	99.11 85	94.80 73	98.36 74	96.28 100	98.60 107	98.12 116	98.44 75	99.76 45	99.87 20

baseline1		97.58 72	98.05 88	97.02 72	96.21 105	99.45 76	97.71 121	93.71 88	98.47 154	95.75 49	98.78 53	93.20 143	98.91 69	98.52 92	98.44 75	99.81 25	99.53 164

NCCC		99.05 28	99.08 46	99.02 21	99.62 25	99.38 99	99.43 33	98.21 23	99.36 39	97.66 27	97.79 88	99.90 37	99.45 26	99.17 35	98.43 77	99.77 43	99.51 172

hybridcas		97.23 88	97.70 111	96.69 82	95.70 132	99.48 68	98.27 91	93.27 109	99.23 56	94.08 89	95.30 169	92.92 144	98.98 64	98.79 66	98.41 78	99.83 15	99.75 77

PVSNet_BlendedMVS		97.51 75	97.71 106	97.28 62	98.06 69	99.61 42	97.31 147	95.02 56	99.08 90	95.51 52	98.05 81	90.11 175	98.07 128	98.91 57	98.40 79	99.72 85	99.78 55

PVSNet_Blended		97.51 75	97.71 106	97.28 62	98.06 69	99.61 42	97.31 147	95.02 56	99.08 90	95.51 52	98.05 81	90.11 175	98.07 128	98.91 57	98.40 79	99.72 85	99.78 55

train_agg		98.73 39	99.11 44	98.28 38	99.36 43	99.35 110	99.48 28	97.96 37	98.83 121	93.86 95	98.70 60	99.86 42	99.44 27	99.08 43	98.38 81	99.61 153	99.58 154

CDS-MVSNet		96.59 134	98.02 92	94.92 144	94.45 180	98.96 145	97.46 139	91.75 139	97.86 192	90.07 161	96.02 145	97.25 90	96.21 183	98.04 130	98.38 81	99.60 161	99.65 139
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HPM-MVS++		99.10 24	99.30 35	98.86 26	99.69 10	99.48 68	99.59 19	98.34 6	99.26 53	96.55 40	99.10 34	99.96 13	99.36 32	99.25 30	98.37 83	99.64 143	99.66 136

MCST-MVS		99.11 23	99.27 37	98.93 24	99.67 16	99.33 118	99.51 24	98.31 11	99.28 49	96.57 39	99.10 34	99.90 37	99.71 2	99.19 34	98.35 84	99.82 17	99.71 114

MSDG		98.27 54	98.29 75	98.24 39	99.20 48	99.22 132	99.20 40	97.82 39	99.37 35	94.43 83	95.90 149	97.31 88	99.12 53	98.76 70	98.35 84	99.67 127	99.14 202

test0.0.03 1		96.69 122	98.12 86	95.01 143	95.49 161	98.99 142	95.86 193	90.82 161	98.38 163	92.54 131	96.66 125	97.33 87	95.75 203	97.75 153	98.34 86	99.60 161	99.40 183

GBi-Net		96.98 101	98.00 93	95.78 132	93.81 187	97.98 199	98.09 103	91.32 152	98.80 126	93.92 92	97.21 102	95.94 107	97.89 135	98.07 123	98.34 86	99.68 118	99.67 132

test1		96.98 101	98.00 93	95.78 132	93.81 187	97.98 199	98.09 103	91.32 152	98.80 126	93.92 92	97.21 102	95.94 107	97.89 135	98.07 123	98.34 86	99.68 118	99.67 132

FMVSNet1		95.77 155	96.41 179	95.03 142	93.42 196	97.86 206	97.11 161	89.89 176	98.53 151	92.00 144	89.17 233	93.23 142	98.15 125	98.07 123	98.34 86	99.61 153	99.69 122

E6new		96.66 128	97.04 148	96.21 110	95.52 156	99.46 72	97.65 130	93.22 114	98.40 161	92.26 139	95.22 171	90.02 178	98.89 74	98.06 127	98.30 90	99.74 58	99.79 47

E6		96.66 128	97.04 148	96.21 110	95.52 156	99.46 72	97.65 130	93.22 114	98.40 161	92.26 139	95.22 171	90.02 178	98.89 74	98.06 127	98.30 90	99.74 58	99.79 47

diffmvs_AUTHOR		96.68 124	97.10 141	96.19 116	95.71 130	99.37 105	97.91 109	93.19 121	99.36 39	91.97 145	95.90 149	89.02 186	98.67 102	98.01 133	98.30 90	99.68 118	99.74 86

viewmanbaseed2359cas		96.92 107	97.60 113	96.14 119	95.71 130	99.44 85	97.82 113	93.39 92	98.93 108	91.34 153	96.10 143	92.27 151	98.82 82	98.40 99	98.30 90	99.75 51	99.75 77

EIA-MVS		97.70 69	98.78 62	96.44 97	95.72 129	99.65 25	98.14 100	93.72 87	98.30 169	92.31 136	98.63 61	97.90 81	98.97 66	98.92 56	98.30 90	99.78 37	99.80 39

UGNet		97.66 70	99.07 48	96.01 128	97.19 85	99.65 25	97.09 162	93.39 92	99.35 41	94.40 85	98.79 52	99.59 58	94.24 233	98.04 130	98.29 95	99.73 72	99.80 39
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
E2		97.34 80	98.05 88	96.50 94	95.61 142	99.43 88	97.83 112	93.38 95	99.15 74	93.69 102	97.79 88	93.65 135	98.79 84	98.36 101	98.28 96	99.73 72	99.73 97

viewmacassd2359aftdt		96.50 136	97.01 151	95.91 130	95.65 139	99.45 76	97.65 130	93.31 104	98.36 165	90.30 159	94.48 182	90.82 167	98.77 89	97.91 142	98.26 97	99.76 45	99.77 62

IterMVS-LS		96.12 148	97.48 118	94.53 148	95.19 169	97.56 224	97.15 158	89.19 191	99.08 90	88.23 168	94.97 174	94.73 120	97.84 140	97.86 147	98.26 97	99.60 161	99.88 18
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous202405211			97.40 127		96.45 96	99.54 58	98.08 106	93.79 83	98.24 173		93.55 189	94.41 125	98.88 78	98.04 130	98.24 99	99.75 51	99.76 69

E3new		96.98 101	97.47 121	96.40 99	95.57 150	99.44 85	97.67 126	93.32 101	98.72 139	93.30 110	96.50 133	91.42 162	98.83 81	98.28 106	98.21 100	99.73 72	99.74 86

viewcassd2359sk11		97.19 91	97.82 100	96.44 97	95.59 148	99.43 88	97.70 122	93.35 97	99.15 74	93.50 105	97.20 106	92.68 147	98.77 89	98.38 100	98.21 100	99.73 72	99.73 97

EPNet_dtu		96.30 142	98.53 68	93.70 169	98.97 53	98.24 193	97.36 144	94.23 75	98.85 116	79.18 231	99.19 25	98.47 75	94.09 235	97.89 145	98.21 100	98.39 234	98.85 214
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		99.14 22	99.20 41	99.06 17	99.58 29	99.53 59	99.45 30	97.80 40	99.19 65	98.32 16	98.58 63	99.95 18	99.60 7	99.28 29	98.20 103	99.64 143	99.69 122

E4		96.62 132	96.98 154	96.21 110	95.53 153	99.45 76	97.68 124	93.28 108	98.43 156	92.18 143	94.78 178	90.21 174	98.86 79	98.00 134	98.19 104	99.74 58	99.75 77

E3		96.98 101	97.49 116	96.39 100	95.60 145	99.44 85	97.68 124	93.32 101	98.80 126	93.19 112	96.50 133	91.49 160	98.80 83	98.28 106	98.19 104	99.73 72	99.74 86

HyFIR lowres test		95.99 151	96.56 166	95.32 140	97.99 72	99.65 25	96.54 178	88.86 197	98.44 155	89.77 165	84.14 259	97.05 92	99.03 61	98.55 90	98.19 104	99.73 72	99.86 23

diffmvs		96.83 112	97.33 130	96.25 105	95.76 125	99.34 113	98.06 107	93.22 114	99.43 29	92.30 137	96.90 118	89.83 182	98.55 109	98.00 134	98.14 107	99.64 143	99.70 117
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E5new		96.68 124	97.05 146	96.24 106	95.52 156	99.45 76	97.67 126	93.33 99	98.42 158	92.41 133	95.34 167	90.30 172	98.79 84	97.94 138	98.13 108	99.74 58	99.74 86

E5		96.68 124	97.05 146	96.24 106	95.52 156	99.45 76	97.67 126	93.33 99	98.42 158	92.41 133	95.34 167	90.30 172	98.79 84	97.94 138	98.13 108	99.74 58	99.74 86

TAPA-MVS	97.53 5	98.41 49	98.84 61	97.91 47	99.08 51	99.33 118	99.15 43	97.13 44	99.34 43	93.20 111	97.75 91	99.19 64	99.20 43	98.66 78	98.13 108	99.66 132	99.48 176
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	97.93 2	99.02 31	98.94 56	99.11 13	99.46 38	99.24 128	99.06 50	97.96 37	99.31 45	99.16 5	97.90 86	99.79 49	99.36 32	98.71 76	98.12 111	99.65 137	99.52 167
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
onestephybrid01		96.90 108	97.41 126	96.31 103	95.85 117	99.34 113	97.43 141	93.35 97	99.39 32	93.17 114	95.53 164	92.12 154	98.40 116	97.73 154	98.11 112	99.65 137	99.68 127

DPM-MVS		98.31 53	98.53 68	98.05 43	98.76 59	98.77 155	99.13 44	98.07 33	99.10 86	94.27 88	96.70 123	99.84 45	98.70 96	97.90 144	98.11 112	99.40 206	99.28 189

Anonymous20231211		97.10 95	97.06 145	97.14 66	96.32 99	99.52 62	98.16 98	93.76 84	98.84 120	95.98 46	90.92 215	94.58 124	98.90 71	97.72 156	98.10 114	99.71 96	99.75 77

gg-mvs-nofinetune		90.85 241	94.14 211	87.02 249	94.89 175	99.25 126	98.64 68	76.29 267	88.24 269	57.50 274	79.93 265	95.45 110	95.18 222	98.77 69	98.07 115	99.62 151	99.24 194

viewmamba		96.88 110	97.43 124	96.23 108	95.81 124	99.35 110	97.57 134	93.17 125	99.46 23	92.46 132	96.40 138	91.48 161	98.72 95	97.59 165	98.05 116	99.63 149	99.68 127

CANet_DTU		96.64 130	99.08 46	93.81 164	97.10 87	99.42 93	98.85 61	90.01 172	99.31 45	79.98 227	99.78 2	99.10 67	97.42 153	98.35 102	98.05 116	99.47 195	99.53 164

Fast-Effi-MVS+		95.38 163	96.52 169	94.05 161	94.15 182	99.14 136	97.24 152	86.79 221	98.53 151	87.62 175	94.51 180	87.06 195	98.76 91	98.60 86	98.04 118	99.72 85	99.77 62

viewdifsd2359ckpt13		96.93 105	97.71 106	96.03 126	95.58 149	99.43 88	97.42 142	93.30 107	99.09 87	91.43 151	96.95 115	92.45 148	98.70 96	98.30 105	97.98 119	99.72 85	99.73 97

GG-mvs-BLEND		69.11 264	98.13 85	35.26 268	3.49 284	98.20 195	94.89 213	2.38 278	98.42 158	5.82 285	96.37 139	98.60 72	5.97 280	98.75 72	97.98 119	99.01 224	98.61 225

viewdifsd2359ckpt09		97.00 100	97.68 112	96.21 110	95.54 152	99.40 97	97.73 120	93.31 104	99.17 67	92.24 141	96.62 127	92.71 145	98.76 91	98.19 113	97.95 121	99.66 132	99.71 114

hybrid		96.87 111	97.45 122	96.19 116	95.83 119	99.32 121	97.44 140	93.21 119	99.44 27	92.66 124	97.41 98	90.38 171	98.39 117	97.93 140	97.94 122	99.59 167	99.70 117

hybridnocas07		96.80 114	97.32 131	96.20 115	95.82 122	99.34 113	97.56 135	93.20 120	99.45 25	92.55 130	96.73 121	90.52 169	98.44 114	97.51 170	97.93 123	99.64 143	99.75 77

Effi-MVS+		95.81 154	97.31 135	94.06 160	95.09 170	99.35 110	97.24 152	88.22 208	98.54 150	85.38 191	98.52 64	88.68 188	98.70 96	98.32 103	97.93 123	99.74 58	99.84 27

GeoE		95.98 153	97.24 137	94.51 149	95.02 172	99.38 99	98.02 108	87.86 214	98.37 164	87.86 173	92.99 204	93.54 136	98.56 108	98.61 83	97.92 125	99.73 72	99.85 26

MIMVSNet		94.49 185	97.59 114	90.87 225	91.74 221	98.70 164	94.68 226	78.73 261	97.98 184	83.71 203	97.71 94	94.81 119	96.96 163	97.97 136	97.92 125	99.40 206	98.04 241

DI_MVS_pp		96.90 108	97.49 116	96.21 110	95.61 142	99.40 97	98.72 66	92.11 132	99.14 79	92.98 119	93.08 202	95.14 114	98.13 126	98.05 129	97.91 127	99.74 58	99.73 97

testgi		95.67 157	97.48 118	93.56 172	95.07 171	99.00 139	95.33 204	88.47 205	98.80 126	86.90 180	97.30 100	92.33 150	95.97 192	97.66 159	97.91 127	99.60 161	99.38 185

thres100view900		96.72 120	96.47 174	97.00 75	96.31 100	99.52 62	98.28 89	94.01 77	97.35 205	94.52 78	95.90 149	86.93 198	99.09 57	98.07 123	97.87 129	99.81 25	99.63 147

dtuplus		96.76 116	97.19 138	96.26 104	95.48 163	99.38 99	97.81 115	93.18 124	98.69 141	92.60 127	95.24 170	92.14 153	98.75 93	97.27 182	97.86 130	99.73 72	99.74 86

casdiffseed414692147		96.17 145	96.26 182	96.06 123	95.50 160	99.38 99	97.34 146	93.13 126	98.09 179	91.89 147	93.14 199	87.49 192	98.78 87	98.12 116	97.86 130	99.75 51	99.77 62

viewmambaseed2359dif		96.82 113	97.19 138	96.39 100	95.64 140	99.38 99	98.15 99	93.24 111	98.78 133	92.85 122	95.93 148	91.24 163	98.75 93	97.41 174	97.86 130	99.70 106	99.74 86

COLMAP_ROB	96.15 12	97.78 65	98.17 83	97.32 60	98.84 54	99.45 76	99.28 38	95.43 53	99.48 22	91.80 149	94.83 177	98.36 77	98.90 71	98.09 120	97.85 133	99.68 118	99.15 199
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AdaColmap		99.06 27	98.98 55	99.15 9	99.60 27	99.30 122	99.38 35	98.16 25	99.02 99	98.55 11	98.71 59	99.57 60	99.58 12	99.09 41	97.84 134	99.64 143	99.36 186

thres200		96.76 116	96.53 168	97.03 70	96.31 100	99.67 20	98.37 83	93.99 79	97.68 200	94.49 81	95.83 155	86.77 200	99.18 47	98.26 108	97.82 135	99.82 17	99.66 136

tfpn200view9		96.75 118	96.51 170	97.03 70	96.31 100	99.67 20	98.41 80	93.99 79	97.35 205	94.52 78	95.90 149	86.93 198	99.14 52	98.26 108	97.80 136	99.82 17	99.70 117

thres400		96.71 121	96.45 176	97.02 72	96.28 103	99.63 34	98.41 80	94.00 78	97.82 194	94.42 84	95.74 156	86.26 206	99.18 47	98.20 112	97.79 137	99.81 25	99.70 117

FC-MVSNet-train		97.04 98	97.91 98	96.03 126	96.00 111	98.41 185	96.53 180	93.42 91	99.04 98	93.02 117	98.03 83	94.32 127	97.47 152	97.93 140	97.77 138	99.75 51	99.88 18

baseline2		96.36 141	97.82 100	94.65 147	94.60 179	99.09 137	96.45 182	89.63 181	98.36 165	91.29 155	97.60 96	94.13 130	96.37 180	98.45 95	97.70 139	99.54 185	99.41 181

IterMVS-SCA-FT		94.89 173	97.87 99	91.42 212	94.86 176	97.70 210	97.24 152	84.88 237	98.93 108	75.74 244	94.26 184	98.25 78	96.69 170	98.52 92	97.68 140	99.10 223	99.73 97

viewdifsd2359ckpt11		96.47 137	96.78 160	96.10 122	95.69 134	99.24 128	97.16 156	93.19 121	99.37 35	92.90 121	95.88 153	89.35 184	98.69 99	96.32 209	97.65 141	98.99 225	99.68 127

viewmsd2359difaftdt		96.47 137	96.78 160	96.11 121	95.69 134	99.24 128	97.16 156	93.19 121	99.35 41	92.93 120	95.88 153	89.34 185	98.69 99	96.31 210	97.65 141	98.99 225	99.68 127

thres600view7		96.69 122	96.43 178	97.00 75	96.28 103	99.67 20	98.41 80	93.99 79	97.85 193	94.29 87	95.96 146	85.91 209	99.19 44	98.26 108	97.63 143	99.82 17	99.73 97

PMMVS		97.52 74	98.39 72	96.51 93	95.82 122	98.73 162	97.80 116	93.05 128	98.76 135	94.39 86	99.07 37	97.03 93	98.55 109	98.31 104	97.61 144	99.43 201	99.21 196

IterMVS		94.81 176	97.71 106	91.42 212	94.83 177	97.63 217	97.38 143	85.08 234	98.93 108	75.67 245	94.02 185	97.64 84	96.66 173	98.45 95	97.60 145	98.90 228	99.72 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Effi-MVS+-dtu		95.74 156	98.04 90	93.06 184	93.92 183	99.16 134	97.90 110	88.16 210	99.07 95	82.02 215	98.02 84	94.32 127	96.74 169	98.53 91	97.56 146	99.61 153	99.62 149

gm-plane-assit		89.44 250	92.82 236	85.49 253	91.37 234	95.34 254	79.55 273	82.12 244	91.68 267	64.79 271	87.98 244	80.26 254	95.66 206	98.51 94	97.56 146	99.45 197	98.41 233

LGP-MVS_train		96.23 143	96.89 155	95.46 139	97.32 80	98.77 155	98.81 63	93.60 89	98.58 147	85.52 189	99.08 36	86.67 202	97.83 141	97.87 146	97.51 148	99.69 110	99.73 97

ACMMP		98.74 38	99.03 53	98.40 35	99.36 43	99.64 31	99.20 40	97.75 41	98.82 123	95.24 65	98.85 50	99.87 41	99.17 49	98.74 74	97.50 149	99.71 96	99.76 69
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CR-MVSNet		94.57 184	97.34 129	91.33 215	94.90 174	98.59 172	97.15 158	79.14 257	97.98 184	80.42 223	96.59 131	93.50 138	96.85 166	98.10 118	97.49 150	99.50 191	99.15 199

PatchT		93.96 193	97.36 128	90.00 236	94.76 178	98.65 167	90.11 255	78.57 262	97.96 187	80.42 223	96.07 144	94.10 131	96.85 166	98.10 118	97.49 150	99.26 216	99.15 199

FC-MVSNet-test		96.07 149	97.94 96	93.89 162	93.60 192	98.67 166	96.62 177	90.30 171	98.76 135	88.62 166	95.57 162	97.63 85	94.48 229	97.97 136	97.48 152	99.71 96	99.52 167

UniMVSNet_ETH3D		93.15 207	92.33 241	94.11 158	93.91 184	98.61 171	94.81 221	90.98 158	97.06 214	87.51 176	82.27 263	76.33 266	97.87 139	94.79 237	97.47 153	99.56 179	99.81 37

PCF-MVS	97.50 6	98.18 58	98.35 74	97.99 45	98.65 60	99.36 107	98.94 58	98.14 29	98.59 146	93.62 103	96.61 128	99.76 52	99.03 61	97.77 151	97.45 154	99.57 176	98.89 213
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchMatch-RL		97.77 66	98.25 77	97.21 65	99.11 50	99.25 126	97.06 165	94.09 76	98.72 139	95.14 68	98.47 69	96.29 99	98.43 115	98.65 79	97.44 155	99.45 197	98.94 208

TAMVS		95.53 159	96.50 172	94.39 153	93.86 186	99.03 138	96.67 175	89.55 183	97.33 207	90.64 157	93.02 203	91.58 159	96.21 183	97.72 156	97.43 156	99.43 201	99.36 186

LTVRE_ROB	93.20 16	92.84 212	94.92 197	90.43 233	92.83 198	98.63 168	97.08 163	87.87 213	97.91 189	68.42 267	93.54 190	79.46 260	96.62 174	97.55 168	97.40 157	99.74 58	99.92 3
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
MVSTER		97.16 92	97.71 106	96.52 92	95.97 113	98.48 178	98.63 69	92.10 133	98.68 142	95.96 47	99.23 24	91.79 157	96.87 165	98.76 70	97.37 158	99.57 176	99.68 127

Baseline_NR-MVSNet		93.87 195	93.98 218	93.75 166	91.66 223	97.02 239	95.53 199	91.52 148	97.16 213	87.77 174	87.93 246	83.69 225	96.35 181	95.10 233	97.23 159	99.68 118	99.73 97

FMVSNet5		95.42 161	96.47 174	94.20 155	92.26 208	95.99 248	95.66 196	87.15 219	97.87 191	93.46 107	96.68 124	93.79 133	97.52 149	97.10 189	97.21 160	99.11 222	96.62 261

pm-mvs1		94.27 186	95.57 191	92.75 188	92.58 201	98.13 196	94.87 215	90.71 165	96.70 224	83.78 200	89.94 228	89.85 181	94.96 226	97.58 167	97.07 161	99.61 153	99.72 111

dtuonly		94.95 170	96.84 158	92.74 189	93.54 194	98.69 165	97.08 163	89.98 173	97.82 194	78.62 234	92.78 205	94.68 121	98.05 132	97.68 158	97.05 162	99.13 221	99.20 197

Fast-Effi-MVS+-dtu		95.38 163	98.20 82	92.09 198	93.91 184	98.87 149	97.35 145	85.01 236	99.08 90	81.09 219	98.10 80	96.36 98	95.62 208	98.43 98	97.03 163	99.55 181	99.50 174

TransMVSNet (Re)		93.45 201	94.08 214	92.72 190	92.83 198	97.62 220	94.94 211	91.54 147	95.65 242	83.06 208	88.93 236	83.53 230	94.25 232	97.41 174	97.03 163	99.67 127	98.40 236

DU-MVS		93.98 192	94.44 208	93.44 176	91.66 223	97.77 207	95.03 207	91.57 145	97.17 211	86.12 182	93.13 200	81.13 249	96.60 175	95.10 233	97.01 165	99.67 127	99.80 39

TSAR-MVS + COLMAP		96.79 115	96.55 167	97.06 68	97.70 75	98.46 180	99.07 49	96.23 47	99.38 33	91.32 154	98.80 51	85.61 211	98.69 99	97.64 163	96.92 166	99.37 209	99.06 206

CLD-MVS		96.74 119	96.51 170	97.01 74	96.71 94	98.62 169	98.73 65	94.38 72	98.94 106	94.46 82	97.33 99	87.03 196	98.07 128	97.20 185	96.87 167	99.72 85	99.54 163
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		93.67 198	94.14 211	93.13 183	91.28 237	97.58 222	95.60 198	91.97 136	97.06 214	84.05 196	90.64 224	82.22 244	96.17 186	94.94 236	96.78 168	99.69 110	99.78 55

RPMNet		94.66 178	97.16 140	91.75 208	94.98 173	98.59 172	97.00 166	78.37 263	97.98 184	83.78 200	96.27 140	94.09 132	96.91 164	97.36 177	96.73 169	99.48 193	99.09 204

UniMVSNet_NR-MVSNet		94.59 182	95.47 192	93.55 173	91.85 218	97.89 205	95.03 207	92.00 135	97.33 207	86.12 182	93.19 197	87.29 194	96.60 175	96.12 215	96.70 170	99.72 85	99.80 39

ET-MVSNet_ETH3D		96.17 145	96.99 152	95.21 141	88.53 253	98.54 175	98.28 89	92.61 129	98.85 116	93.60 104	99.06 38	90.39 170	98.63 105	95.98 221	96.68 171	99.61 153	99.41 181

ACMH	95.42 14	95.27 166	95.96 185	94.45 151	96.83 93	98.78 154	94.72 224	91.67 142	98.95 104	86.82 181	96.42 137	83.67 226	97.00 161	97.48 172	96.68 171	99.69 110	99.76 69
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		96.22 144	95.85 189	96.65 85	97.75 73	98.54 175	99.00 55	95.53 50	96.88 218	89.88 163	95.95 147	86.46 205	98.07 128	97.65 162	96.63 173	99.67 127	98.83 217
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	96.25 10	96.62 132	96.72 162	96.50 94	96.96 89	98.75 159	97.80 116	94.30 74	98.85 116	93.12 115	98.78 53	86.61 203	97.23 158	97.73 154	96.61 174	99.62 151	99.71 114
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dmvs_re		96.02 150	96.49 173	95.47 138	93.49 195	99.26 125	97.25 151	93.82 82	97.51 202	90.43 158	97.52 97	87.93 190	98.12 127	96.86 193	96.59 175	99.73 72	99.76 69

ACMH+	95.51 13	95.40 162	96.00 183	94.70 146	96.33 98	98.79 152	96.79 170	91.32 152	98.77 134	87.18 177	95.60 161	85.46 212	96.97 162	97.15 186	96.59 175	99.59 167	99.65 139

CP-MVSNet		93.25 205	94.00 217	92.38 193	91.65 225	97.56 224	94.38 233	89.20 190	96.05 236	83.16 207	89.51 230	81.97 245	96.16 187	96.43 203	96.56 177	99.71 96	99.89 13

HQP-MVS		96.37 140	96.58 165	96.13 120	97.31 82	98.44 182	98.45 77	95.22 54	98.86 114	88.58 167	98.33 75	87.00 197	97.67 144	97.23 183	96.56 177	99.56 179	99.62 149

FA-MVS(training)		96.52 135	98.29 75	94.45 151	95.88 116	99.52 62	97.66 129	81.47 245	98.94 106	93.79 99	95.54 163	99.11 66	98.29 120	98.89 59	96.49 179	99.63 149	99.52 167

PS-CasMVS		92.72 217	93.36 229	91.98 202	91.62 227	97.52 226	94.13 237	88.98 195	95.94 239	81.51 218	87.35 248	79.95 257	95.91 193	96.37 205	96.49 179	99.70 106	99.89 13

Anonymous20231206		90.70 245	93.93 219	86.92 250	90.21 245	96.79 242	90.30 254	86.61 225	96.05 236	69.25 264	88.46 240	84.86 218	85.86 262	97.11 188	96.47 181	99.30 213	97.80 246

MVS-HIRNet		92.51 221	95.97 184	88.48 245	93.73 190	98.37 188	90.33 253	75.36 269	98.32 168	77.78 238	89.15 234	94.87 117	95.14 223	97.62 164	96.39 182	98.51 231	97.11 254

DTE-MVSNet		92.42 226	92.85 234	91.91 205	90.87 241	96.97 240	94.53 232	89.81 177	95.86 241	81.59 217	88.83 237	77.88 264	95.01 225	94.34 240	96.35 183	99.64 143	99.73 97

ACMM	96.26 9	96.67 127	96.69 163	96.66 84	97.29 83	98.46 180	96.48 181	95.09 55	99.21 62	93.19 112	98.78 53	86.73 201	98.17 122	97.84 148	96.32 184	99.74 58	99.49 175
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EU-MVSNet		92.80 214	94.76 202	90.51 231	91.88 216	96.74 244	92.48 244	88.69 202	96.21 231	79.00 232	91.51 211	87.82 191	91.83 254	95.87 223	96.27 185	99.21 217	98.92 212

PEN-MVS		92.72 217	93.20 231	92.15 197	91.29 235	97.31 235	94.67 227	89.81 177	96.19 232	81.83 216	88.58 239	79.06 261	95.61 209	95.21 230	96.27 185	99.72 85	99.82 32

TinyColmap		94.00 191	94.35 209	93.60 170	95.89 114	98.26 191	97.49 138	88.82 198	98.56 149	83.21 206	91.28 214	80.48 253	96.68 171	97.34 178	96.26 187	99.53 187	98.24 237

test-mter		94.86 174	97.32 131	92.00 201	92.41 205	98.82 151	96.18 189	86.35 227	98.05 181	82.28 213	96.48 135	94.39 126	95.46 215	98.17 115	96.20 188	99.32 212	99.13 203

NR-MVSNet		94.01 190	94.51 206	93.44 176	92.56 202	97.77 207	95.67 195	91.57 145	97.17 211	85.84 186	93.13 200	80.53 252	95.29 219	97.01 190	96.17 189	99.69 110	99.75 77

tfpnnormal		93.85 197	94.12 213	93.54 174	93.22 197	98.24 193	95.45 201	91.96 137	94.61 245	83.91 198	90.74 221	81.75 247	97.04 160	97.49 171	96.16 190	99.68 118	99.84 27

USDC		94.26 187	94.83 200	93.59 171	96.02 109	98.44 182	97.84 111	88.65 203	98.86 114	82.73 212	94.02 185	80.56 251	96.76 168	97.28 181	96.15 191	99.55 181	98.50 228

thisisatest0530		97.23 88	98.25 77	96.05 124	95.60 145	99.59 49	96.96 167	93.23 112	99.17 67	92.60 127	98.75 56	96.19 101	98.17 122	98.19 113	96.10 192	99.72 85	99.77 62

tttt0517		97.23 88	98.24 80	96.04 125	95.60 145	99.60 47	96.94 168	93.23 112	99.15 74	92.56 129	98.74 57	96.12 104	98.17 122	98.21 111	96.10 192	99.73 72	99.78 55

test-LLR		95.50 160	97.32 131	93.37 178	95.49 161	98.74 160	96.44 183	90.82 161	98.18 174	82.75 210	96.60 129	94.67 122	95.54 211	98.09 120	96.00 194	99.20 218	98.93 209

TESTMET0.1,1		94.95 170	97.32 131	92.20 196	92.62 200	98.74 160	96.44 183	86.67 223	98.18 174	82.75 210	96.60 129	94.67 122	95.54 211	98.09 120	96.00 194	99.20 218	98.93 209

EG-PatchMatch MVS		92.45 222	93.92 220	90.72 230	92.56 202	98.43 184	94.88 214	84.54 239	97.18 210	79.55 229	86.12 256	83.23 237	93.15 247	97.22 184	96.00 194	99.67 127	99.27 192

UniMVSNet (Re)		94.58 183	95.34 193	93.71 168	92.25 209	98.08 197	94.97 209	91.29 157	97.03 216	87.94 171	93.97 187	86.25 207	96.07 188	96.27 212	95.97 197	99.72 85	99.79 47

anonymousdsp		93.12 208	95.86 188	89.93 238	91.09 238	98.25 192	95.12 205	85.08 234	97.44 204	73.30 256	90.89 216	90.78 168	95.25 221	97.91 142	95.96 198	99.71 96	99.82 32

WR-MVS_H		93.54 199	94.67 204	92.22 194	91.95 214	97.91 204	94.58 230	88.75 199	96.64 225	83.88 199	90.66 223	85.13 215	94.40 230	96.54 201	95.91 199	99.73 72	99.89 13

usedtu_dtu_shiyan1		94.86 174	96.31 180	93.16 182	88.71 251	98.02 198	96.17 190	91.31 156	98.43 156	87.18 177	91.68 210	93.37 139	96.06 189	97.46 173	95.83 200	99.53 187	99.40 183

WR-MVS		93.43 203	94.48 207	92.21 195	91.52 230	97.69 212	94.66 228	89.98 173	96.86 219	83.43 204	90.12 225	85.03 216	93.94 238	96.02 219	95.82 201	99.71 96	99.82 32

IB-MVS	93.96 15	95.02 169	96.44 177	93.36 179	97.05 88	99.28 123	90.43 252	93.39 92	98.02 182	96.02 45	94.92 176	92.07 155	83.52 264	95.38 227	95.82 201	99.72 85	99.59 153
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
pmmvs6		91.90 236	92.53 239	91.17 219	91.81 219	97.63 217	93.23 239	88.37 207	93.43 262	80.61 221	77.32 268	87.47 193	94.12 234	96.58 199	95.72 203	98.88 229	99.53 164

MS-PatchMatch		95.99 151	97.26 136	94.51 149	97.46 77	98.76 158	97.27 149	86.97 220	99.09 87	89.83 164	93.51 192	97.78 83	96.18 185	97.53 169	95.71 204	99.35 210	98.41 233

MDTV_nov1_ep13		95.57 158	97.48 118	93.35 180	95.43 164	98.97 144	97.19 155	83.72 243	98.92 111	87.91 172	97.75 91	96.12 104	97.88 138	96.84 195	95.64 205	97.96 240	98.10 240

MIMVSNet1		88.61 251	90.68 253	86.19 252	81.56 267	95.30 255	87.78 265	85.98 230	94.19 249	72.30 262	78.84 266	78.90 262	90.06 255	96.59 198	95.47 206	99.46 196	95.49 263

RPSCF		97.61 71	98.16 84	96.96 77	98.10 68	99.00 139	98.84 62	93.76 84	99.45 25	94.78 74	99.39 19	99.31 62	98.53 111	96.61 197	95.43 207	97.74 242	97.93 245

pmmvs4		95.09 167	95.90 186	94.14 157	92.29 207	97.70 210	95.45 201	90.31 169	98.60 145	90.70 156	93.25 196	89.90 180	96.67 172	97.13 187	95.42 208	99.44 199	99.28 189

GA-MVS		93.93 194	96.31 180	91.16 220	93.61 191	98.79 152	95.39 203	90.69 166	98.25 172	73.28 257	96.15 142	88.42 189	94.39 231	97.76 152	95.35 209	99.58 172	99.45 178

v10		92.79 215	94.06 215	91.31 216	91.78 220	97.29 237	94.87 215	86.10 229	96.97 217	79.82 228	88.16 242	84.56 219	95.63 207	96.33 208	95.31 210	99.65 137	99.80 39

v1192		92.43 225	93.61 224	91.05 221	91.53 229	97.43 230	94.61 229	87.99 212	96.60 226	76.72 240	87.11 251	82.74 242	95.85 197	96.35 207	95.30 211	99.60 161	99.74 86

test_method		87.27 255	91.58 245	82.25 259	75.65 273	87.52 273	86.81 267	72.60 270	97.51 202	73.20 258	85.07 258	79.97 256	88.69 257	97.31 179	95.24 212	96.53 266	98.41 233

v1144		92.81 213	94.03 216	91.40 214	91.68 222	97.60 221	94.73 223	88.40 206	96.71 223	78.48 235	88.14 243	84.46 221	95.45 216	96.31 210	95.22 213	99.65 137	99.76 69

v1240		91.99 235	93.33 230	90.44 232	91.29 235	97.30 236	94.25 235	86.79 221	96.43 229	75.49 247	86.34 255	81.85 246	95.29 219	96.42 204	95.22 213	99.52 189	99.73 97

v144192		92.38 227	93.55 227	91.00 222	91.44 231	97.47 229	94.27 234	87.41 217	96.52 228	78.03 236	87.50 247	82.65 243	95.32 218	95.82 224	95.15 215	99.55 181	99.78 55

v1921920		92.36 229	93.57 225	90.94 223	91.39 233	97.39 232	94.70 225	87.63 216	96.60 226	76.63 241	86.98 252	82.89 240	95.75 203	96.26 213	95.14 216	99.55 181	99.73 97

test20.03		90.65 246	93.71 223	87.09 248	90.44 243	96.24 245	89.74 258	85.46 233	95.59 243	72.99 260	90.68 222	85.33 213	84.41 263	95.94 222	95.10 217	99.52 189	97.06 256

pmmvs5		92.71 219	94.27 210	90.90 224	91.42 232	97.74 209	93.23 239	86.66 224	95.99 238	78.96 233	91.45 212	83.44 235	95.55 210	97.30 180	95.05 218	99.58 172	98.93 209

v7n		91.61 237	92.95 232	90.04 235	90.56 242	97.69 212	93.74 238	85.59 231	95.89 240	76.95 239	86.60 254	78.60 263	93.76 241	97.01 190	94.99 219	99.65 137	99.87 20

v2v482		92.77 216	93.52 228	91.90 206	91.59 228	97.63 217	94.57 231	90.31 169	96.80 222	79.22 230	88.74 238	81.55 248	96.04 191	95.26 229	94.97 220	99.66 132	99.69 122

SCA		94.95 170	97.44 123	92.04 199	95.55 151	99.16 134	96.26 187	79.30 256	99.02 99	85.73 188	98.18 78	97.13 91	97.69 142	96.03 218	94.91 221	97.69 247	97.65 248

v8		92.87 211	93.87 222	91.72 210	92.05 211	97.50 227	94.79 222	88.20 209	96.85 220	80.11 226	90.01 226	82.86 241	95.48 213	95.15 232	94.90 222	99.66 132	99.80 39

V42		93.05 209	93.90 221	92.04 199	91.91 215	97.66 214	94.91 212	89.91 175	96.85 220	80.58 222	89.66 229	83.43 236	95.37 217	95.03 235	94.90 222	99.59 167	99.78 55

SixPastTwentyTwo		93.44 202	95.32 194	91.24 217	92.11 210	98.40 186	92.77 242	88.64 204	98.09 179	77.83 237	93.51 192	85.74 210	96.52 178	96.91 192	94.89 224	99.59 167	99.73 97

tpm		92.38 227	94.79 201	89.56 240	94.30 181	97.50 227	94.24 236	78.97 260	97.72 198	74.93 249	97.97 85	82.91 239	96.60 175	93.65 242	94.81 225	98.33 235	98.98 207

EPMVS		95.05 168	96.86 157	92.94 186	95.84 118	98.96 145	96.68 174	79.87 252	99.05 96	90.15 160	97.12 109	95.99 106	97.49 151	95.17 231	94.75 226	97.59 249	96.96 257

thisisatest0515		94.61 181	96.89 155	91.95 203	92.00 213	98.47 179	92.01 246	90.73 164	98.18 174	83.96 197	94.51 180	95.13 115	93.38 244	97.38 176	94.74 227	99.61 153	99.79 47

v148		92.36 229	92.88 233	91.75 208	91.63 226	97.66 214	92.64 243	90.55 167	96.09 234	83.34 205	88.19 241	80.00 255	92.74 248	93.98 241	94.58 228	99.58 172	99.69 122

TDRefinement		93.04 210	93.57 225	92.41 192	96.58 95	98.77 155	97.78 118	91.96 137	98.12 178	80.84 220	89.13 235	79.87 258	87.78 259	96.44 202	94.50 229	99.54 185	98.15 239

ADS-MVSNet		94.65 179	97.04 148	91.88 207	95.68 137	98.99 142	95.89 192	79.03 259	99.15 74	85.81 187	96.96 114	98.21 80	97.10 159	94.48 239	94.24 230	97.74 242	97.21 253

FE-MVSNET2		87.81 254	88.02 259	87.56 247	80.30 269	96.14 247	90.86 250	87.34 218	93.58 260	74.84 250	71.50 270	65.61 273	92.53 252	96.74 196	94.12 231	99.50 191	98.47 231

PatchmatchNet		94.70 177	97.08 144	91.92 204	95.53 153	98.85 150	95.77 194	79.54 254	98.95 104	85.98 184	98.52 64	96.45 95	97.39 154	95.32 228	94.09 232	97.32 256	97.38 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		89.55 249	90.30 254	88.67 243	87.06 254	95.60 251	90.88 249	84.51 240	96.14 233	75.75 243	86.89 253	63.47 277	94.64 228	96.85 194	93.89 233	99.17 220	99.29 188

FE-MVSNET		86.50 256	88.24 258	84.47 256	76.04 271	94.06 265	87.91 264	86.26 228	92.71 263	69.03 266	77.33 267	66.72 272	88.34 258	95.57 226	93.83 234	99.27 215	97.48 249

pmmvs-eth3d		89.81 248	89.65 256	90.00 236	86.94 255	95.38 253	91.08 247	86.39 226	94.57 246	82.27 214	83.03 262	64.94 274	93.96 237	96.57 200	93.82 235	99.35 210	99.24 194

MDTV_nov1_ep13_2view		92.44 223	95.66 190	88.68 242	91.05 239	97.92 203	92.17 245	79.64 253	98.83 121	76.20 242	91.45 212	93.51 137	95.04 224	95.68 225	93.70 236	97.96 240	98.53 227

new_pmnet		90.45 247	92.84 235	87.66 246	88.96 250	96.16 246	88.71 262	84.66 238	97.56 201	71.91 263	85.60 257	86.58 204	93.28 245	96.07 217	93.54 237	98.46 232	94.39 265

N_pmnet		92.21 232	94.60 205	89.42 241	91.88 216	97.38 233	89.15 261	89.74 180	97.89 190	73.75 254	87.94 245	92.23 152	93.85 240	96.10 216	93.20 238	98.15 239	97.43 251

PatchmatchNet1												92.69 146	93.67 243	96.02 219	93.09 239	98.16 238	97.66 247
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
CostFormer		94.25 188	94.88 199	93.51 175	95.43 164	98.34 190	96.21 188	80.64 249	97.94 188	94.01 90	98.30 76	86.20 208	97.52 149	92.71 245	92.69 240	97.23 259	98.02 243

dtuonlycased		92.09 234	95.05 196	88.64 244	90.98 240	97.03 238	89.54 259	85.55 232	98.13 177	74.33 251	93.51 192	92.03 156	92.59 251	93.63 243	92.52 241	98.85 230	98.50 228

pmmvs3		88.19 252	91.27 246	84.60 255	85.60 257	93.66 266	85.68 268	81.13 247	92.36 265	63.66 273	89.51 230	77.10 265	93.22 246	96.37 205	92.40 242	98.30 236	97.46 250

tpmrst		93.86 196	95.88 187	91.50 211	95.69 134	98.62 169	95.64 197	79.41 255	98.80 126	83.76 202	95.63 160	96.13 103	97.25 156	92.92 244	92.31 243	97.27 257	96.74 258

MDA-MVSNet-bldmvs		87.84 253	89.22 257	86.23 251	81.74 266	96.77 243	83.74 269	89.57 182	94.50 247	72.83 261	96.64 126	64.47 276	92.71 249	81.43 268	92.28 244	96.81 264	98.47 231

Gipuma		81.40 260	81.78 263	80.96 261	83.21 259	85.61 274	79.73 272	76.25 268	97.33 207	64.21 272	55.32 275	55.55 279	86.04 261	92.43 248	92.20 245	96.32 268	93.99 266
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmnet_mix02		92.44 223	94.68 203	89.83 239	92.46 204	97.65 216	89.92 257	90.49 168	98.76 135	73.05 259	91.78 209	90.08 177	94.86 227	94.53 238	91.94 246	98.21 237	98.01 244

ambc			80.99 264		80.04 270	90.84 268	90.91 248		96.09 234	74.18 252	62.81 273	30.59 285	82.44 265	96.25 214	91.77 247	95.91 269	98.56 226

dps		94.63 180	95.31 195	93.84 163	95.53 153	98.71 163	96.54 178	80.12 251	97.81 197	97.21 32	96.98 113	92.37 149	96.34 182	92.46 247	91.77 247	97.26 258	97.08 255

0.4-1-1-0.1		93.46 200	92.78 237	94.25 154	89.58 246	95.89 249	96.90 169	89.00 194	94.50 247	95.29 62	97.21 102	83.62 227	97.58 147	88.01 262	91.72 249	97.15 260	98.48 230

tpm cat1		94.06 189	94.90 198	93.06 184	95.42 166	98.52 177	96.64 176	80.67 248	97.82 194	92.63 126	93.39 195	95.00 116	96.06 189	91.36 251	91.58 250	96.98 262	96.66 260

0.3-1-1-0.015		93.30 204	92.54 238	94.20 155	89.52 248	95.62 250	96.78 171	88.89 196	94.12 250	95.31 58	97.26 101	83.52 231	97.69 142	87.57 264	91.45 251	96.99 261	98.23 238

0.4-1-1-0.2		93.21 206	92.46 240	94.08 159	89.56 247	95.52 252	96.71 172	88.73 200	93.97 258	95.29 62	97.17 108	83.59 228	97.33 155	87.65 263	91.30 252	96.89 263	98.03 242

CMPMVS	70.31 18	90.74 244	91.06 248	90.36 234	97.32 80	97.43 230	92.97 241	87.82 215	93.50 261	75.34 248	83.27 261	84.90 217	92.19 253	92.64 246	91.21 253	96.50 267	94.46 264
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		81.36 261	89.93 255	71.35 264	88.65 252	87.85 272	71.46 275	88.12 211	96.23 230	32.21 280	92.61 206	83.00 238	56.27 274	91.92 250	89.43 254	91.39 273	88.49 269

new-patchmatchnet		86.12 257	87.30 260	84.74 254	86.92 256	95.19 256	83.57 270	84.42 241	92.67 264	65.66 268	80.32 264	64.72 275	89.41 256	92.33 249	89.21 255	98.43 233	96.69 259

PMMVS2		77.26 262	79.47 265	74.70 263	76.00 272	88.37 271	74.22 274	76.34 266	78.31 273	54.13 275	69.96 271	52.50 280	70.14 270	84.83 266	88.71 256	97.35 255	93.58 267

usedtu_dtu_shiyan2		84.24 258	84.83 261	83.55 257	75.12 275	92.45 267	88.33 263	81.21 246	87.18 270	73.36 255	64.78 272	73.58 269	86.68 260	88.73 256	88.30 257	96.59 265	98.82 220

MVE	67.97 19	65.53 267	67.43 272	63.31 267	59.33 277	74.20 275	53.09 280	70.43 271	66.27 276	43.13 276	45.98 279	30.62 284	70.65 269	79.34 270	86.30 258	83.25 277	89.33 268
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
blended_shiyan8		90.91 239	90.97 250	90.84 226	82.45 260	94.62 257	94.96 210	89.15 192	93.94 259	85.03 192	90.85 219	83.58 229	95.78 202	88.79 254	86.19 259	97.70 246	98.80 221

blended_shiyan6		90.91 239	91.00 249	90.80 227	82.44 261	94.60 259	94.86 217	89.05 193	94.08 251	84.93 195	90.75 220	83.74 222	95.81 198	88.79 254	86.19 259	97.71 245	98.83 217

blend_shiyan4		92.70 220	91.74 244	93.81 164	88.98 249	94.51 264	96.29 185	88.71 201	94.00 253	95.31 58	97.12 109	83.52 231	95.91 193	88.20 261	85.99 261	97.69 247	98.84 215

wanda-best-256-512		90.85 241	90.88 251	90.80 227	82.44 261	94.55 260	94.83 218	89.26 186	93.99 254	84.94 193	90.86 217	83.70 223	95.80 199	88.61 257	85.85 262	97.57 250	98.64 223

FE-blended-shiyan7		90.85 241	90.88 251	90.80 227	82.44 261	94.55 260	94.83 218	89.26 186	93.99 254	84.94 193	90.86 217	83.70 223	95.80 199	88.61 257	85.85 262	97.57 250	98.64 223

usedtu_blend_shiyan5		92.28 231	91.78 242	92.86 187	82.44 261	94.55 260	96.69 173	89.26 186	93.99 254	95.31 58	97.12 109	83.52 231	95.91 193	88.61 257	85.85 262	97.57 250	98.84 215

FE-MVSNET3		92.14 233	91.78 242	92.55 191	82.44 261	94.55 260	94.83 218	89.26 186	93.99 254	95.31 58	97.12 109	83.52 231	95.91 193	88.61 257	85.85 262	97.57 250	98.83 217

gbinet_0.2-2-1-0.02		91.19 238	91.20 247	91.18 218	83.37 258	94.62 257	95.06 206	89.43 184	94.06 252	85.87 185	91.99 208	84.54 220	95.79 201	88.81 253	85.62 266	97.56 254	98.74 222

tmp_tt				82.25 259	97.73 74	88.71 270	80.18 271	68.65 272	99.15 74	86.98 179	99.47 14	85.31 214	68.35 271	87.51 265	83.81 267	91.64 271

E-PMN		68.30 265	68.43 269	68.15 265	74.70 276	71.56 277	55.64 278	77.24 264	77.48 275	39.46 277	51.95 278	41.68 283	73.28 268	70.65 271	79.51 268	88.61 275	86.20 272

FPMVS		83.82 259	84.61 262	82.90 258	90.39 244	90.71 269	90.85 251	84.10 242	95.47 244	65.15 269	83.44 260	74.46 267	75.48 266	81.63 267	79.42 269	91.42 272	87.14 270

PMVS	72.60 17	76.39 263	77.66 266	74.92 262	81.04 268	69.37 278	68.47 276	80.54 250	85.39 272	65.07 270	73.52 269	72.91 270	65.67 272	80.35 269	76.81 270	88.71 274	85.25 273
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		68.12 266	68.11 271	68.14 266	75.51 274	71.76 276	55.38 279	77.20 265	77.78 274	37.79 278	53.59 276	43.61 281	74.72 267	67.05 272	76.70 271	88.27 276	86.24 271

VLMVS_CLIP		52.45 270	70.60 268	31.28 271	17.18 280	38.05 281	42.13 282	3.57 277	88.28 268	17.71 283	95.42 166	61.64 278	48.11 276	64.76 273	62.97 272	59.00 278	83.08 274

MVS_clip		53.88 268	72.12 267	32.61 270	20.61 279	45.41 279	36.61 283	4.93 275	91.90 266	24.67 282	89.97 227	74.03 268	57.13 273	61.93 274	58.92 273	51.68 280	82.67 275

VLMVS		52.63 269	68.18 270	34.50 269	22.09 278	38.45 280	42.45 281	4.82 276	85.79 271	35.46 279	89.41 232	67.69 271	49.01 275	57.62 275	58.84 274	53.16 279	79.46 276

testmvs		31.24 271	40.15 274	20.86 272	12.61 281	17.99 282	25.16 284	13.30 273	48.42 278	24.82 281	53.07 277	30.13 286	28.47 277	42.73 276	37.65 275	20.79 281	51.04 278

MVS_baseline		26.32 273	43.96 273	5.74 274	4.07 283	14.12 284	5.93 286	0.00 279	54.17 277	0.00 286	61.72 274	42.95 282	23.20 279	35.99 277	35.87 276	1.21 283	62.88 277

test123		26.75 272	34.25 275	18.01 273	7.93 282	17.18 283	24.85 285	12.36 274	44.83 279	16.52 284	41.80 280	18.10 287	28.29 278	33.08 278	34.79 277	18.10 282	49.95 279

uanet_test		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet-low-res		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

sosnet		0.00 274	0.00 276	0.00 275	0.00 285	0.00 285	0.00 287	0.00 279	0.00 280	0.00 286	0.00 281	0.00 288	0.00 281	0.00 279	0.00 278	0.00 284	0.00 280

ACM-MVS					99.59 28	99.00 139	98.98 56		98.65 144	93.77 100	98.98 41	99.92 31	97.60 146			99.39 208	99.58 154

PatchmatchNet2					92.01 212	97.36 234	89.36 260
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										73.82 253	87.22 250
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.83 1	98.29 14		99.52 4						99.71 96

TPM-MVS					99.57 30	98.90 148	98.79 64			96.52 41	98.62 62	99.91 35	97.56 148			99.44 199	99.28 189
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										69.05 265

9.14												99.79 49

SR-MVS					99.67 16			98.25 18				99.94 27

our_test_3					92.30 206	97.58 222	90.09 256

MTAPA										98.09 19		99.97 9

MTMP										98.46 14		99.96 13

Patchmatch-RL test							66.86 277

XVS					97.42 78	99.62 37	98.59 71			93.81 96		99.95 18				99.69 110

X-MVStestdata					97.42 78	99.62 37	98.59 71			93.81 96		99.95 18				99.69 110

mPP-MVS					99.53 34							99.89 39

NP-MVS									98.57 148

Patchmtry						98.59 172	97.15 158	79.14 257		80.42 223

DeepMVS_CX						96.85 241	87.43 266	89.27 185	98.30 169	75.55 246	95.05 173	79.47 259	92.62 250	89.48 252		95.18 270	95.96 262

High-resolution multi-view benchmark